{"id":"https://openalex.org/W2016717966","doi":"https://doi.org/10.1109/icassp.2009.4960577","title":"WEB-derived pronunciations","display_name":"WEB-derived pronunciations","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2016717966","doi":"https://doi.org/10.1109/icassp.2009.4960577","mag":"2016717966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University, Baltimore, MD, 21218, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University, Baltimore, MD, 21218, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069254823","display_name":"Martin Jansche","orcid":"https://orcid.org/0000-0003-0484-4879"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Jansche","raw_affiliation_strings":["Google, Inc., New York, NY, USA","Google Inc., New York, 10011, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, 10011, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University, Baltimore, MD, 21218, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University, Baltimore, MD, 21218, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Riley","raw_affiliation_strings":["Google, Inc., New York, NY, USA","Google Inc., New York, 10011, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, 10011, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053473331","display_name":"Morgan Ulinski","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morgan Ulinski","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA","Cornell University Ithaca, NY 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University Ithaca, NY 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"wss 3","issue":null,"first_page":"4289","last_page":"4292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8158794641494751},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6323985457420349},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5171403288841248},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48859959840774536},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4818750321865082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44892215728759766},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4366135895252228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42356210947036743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08955037593841553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158794641494751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6323985457420349},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5171403288841248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48859959840774536},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4818750321865082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44892215728759766},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4366135895252228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42356210947036743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08955037593841553},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.8284","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.8284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/~arnab/pubs/WebPron.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.227.6733","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.227.6733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/%7Egpenn/csc2518/ghoshaletal09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W120415783","https://openalex.org/W1506201763","https://openalex.org/W1529355025","https://openalex.org/W1582482241","https://openalex.org/W1779680350","https://openalex.org/W1934041838","https://openalex.org/W1970195330","https://openalex.org/W2063401344","https://openalex.org/W2104770448","https://openalex.org/W2183390198","https://openalex.org/W6630412972","https://openalex.org/W6631608000","https://openalex.org/W6638280674"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W2000745862"],"abstract_inverted_index":{"Pronunciation":[0],"information":[1],"is":[2],"available":[3],"in":[4,10],"large":[5],"quantities":[6],"on":[7,59],"the":[8,11],"Web,":[9],"form":[12],"of":[13],"IPA":[14,40],"and":[15,28,50],"ad-hoc":[16,54],"transcriptions.":[17,55],"We":[18,56],"describe":[19],"techniques":[20],"for":[21],"extracting":[22],"candidate":[23],"pronunciations":[24,41],"from":[25,53],"Web":[26],"pages":[27],"associating":[29],"them":[30],"with":[31],"orthographic":[32],"words,":[33],"filtering":[34],"out":[35],"poorly":[36],"extracted":[37],"pronunciations,":[38],"normalizing":[39],"to":[42,45],"better":[43],"conform":[44],"a":[46,60],"common":[47],"transcription":[48],"standard,":[49],"generating":[51],"phonemic":[52],"show":[57],"improvements":[58],"letter-to-phoneme":[61],"task":[62],"when":[63],"using":[64],"web-derived":[65],"vs.":[66],"Pronlex":[67],"pronunciations.":[68]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
